Is Gemma 3 4B IT or Llama 4 Scout 17B cheaper?

Gemma 3 4B IT is cheaper on output tokens ($0.10 vs $0.30 per 1M).

Which has the larger context window, Gemma 3 4B IT or Llama 4 Scout 17B?

Llama 4 Scout 17B has the larger context window (328K tokens).

Gemma 3 4B IT vs Llama 4 Scout 17B

Gemma 3 4B IT is cheaper on output tokens, while Llama 4 Scout 17B offers a larger context window. Choose Gemma 3 4B IT or Llama 4 Scout 17B based on the trade-off between cost, context, and the benchmarks that matter for your use case.

Spec	Gemma 3 4B IT	Llama 4 Scout 17B
Provider	Deep Infra	Deep Infra
Input / 1M tokens	$0.05	$0.10
Output / 1M tokens	$0.10	$0.30
Context window	131K	328K
Parameters	—	—
Open weights	Yes	Yes
Released	Mar 2025	Apr 2025

Gemma 3 4B IT details →Llama 4 Scout 17B details →

FAQ

Pricing is indicative — confirm with the provider before production use. Highlighted values indicate the better figure for that row.